In LLM agent trajectories, delaying KV cache compaction by a few turns and using the agent's later queries as the compression guide preserves most accuracy while cutting KV cache by 80%.
Once you have a top candidate, you MUST issue additional verification searches from new angles to confirm the candidate satisfies EVERY criterion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Practical Online KV Cache Compaction for LLM Agents: An Empirical Study
In LLM agent trajectories, delaying KV cache compaction by a few turns and using the agent's later queries as the compression guide preserves most accuracy while cutting KV cache by 80%.